Search Results (11)

The complex and variable environment of facility orchards poses significant challenges for intelligent robotic operations. To address issues such as nectarine fruit occlusion by branches and leaves, complex backgrounds, and the demand for high real-time detection performance, this study proposes a target detection model for nectarine fruit based on the YOLOv11 architecture—Ghost–iEMA–ADown You Only Look (GIA-YOLO). We introduce the GhostModule to reduce the model size and the floating-point operations, adopt the fusion attention mechanism iEMA to enhance the feature extraction capability, and further optimize the network structure through the ADown lightweight downsampling module. The test results show that GIA-YOLO achieves 93.9% precision, 88.9% recall, and 96.2% mAP, which are 2.2, 1.1, and 0.7 percentage points higher than YOLOv11, respectively; the size of the model is reduced to 5.0 MB and the floating-point operations is reduced to 5.2 G, which is 9.1% and 17.5% less compared to the original model, respectively. The model was deployed in the picking robot system and field tested in the nectarine facility orchard, the results show that GIA-YOLO maintains high detection precision and stability at different picking distances, with a comprehensive missed detection rate of 6.65%, a false detection rate of 8.7%, and supports real-time detection at 41.6 FPS. The results of the research provide an important reference and support for the optimization of the design and application of the nectarine detection model in the facility agriculture environment. Full article

In alignment with the United Nations’ Sustainable Development Goals (SDGs) 12 (Responsible Consumption and Production) and 13 (Climate Action), this research explores the sustainable valorization of mangosteen peels into mangosteen peel powder (MPP), a value-added product with pharmaceutical properties. Mangosteen peels are an abundant agricultural waste in Thailand. This study evaluates six MPP production schemes, each employing different drying methods. Life Cycle Assessment (LCA) is utilized to assess the global warming potential (GWP) of these schemes, and the quality of the MPP produced is also compared. The results show that a combination of frozen storage and freeze-drying (scheme 4) has the highest GWP (1091.897 kgCO₂eq) due to substantial electricity usage, whereas a combination of frozen storage and sun-drying (scheme 5) has the lowest GWP (0.031 kgCO₂eq) but is prone to microbial contamination. Frozen storage without coarse grinding, combined with hot-air drying (scheme 6), is identified as the optimal scheme in terms of GWP (11.236 kgCO₂eq) and product quality. Due to the lack of an onsite hot-air-drying facility, two transportation strategies are integrated into scheme 6 for scenarios A and B. These transportation strategies include transporting mangosteen peels from orchards to a facility in another province or transporting a mobile hot-air-drying unit to the orchards. The analysis indicates that scenario B is more favorable both operationally and environmentally, due to its lower emissions. This research is the first to comparatively assess the GWP of different MPP production schemes using LCA. Furthermore, it aligns with the growing trend in international trade which places greater emphasis on environmentally friendly production processes. Full article

The acute shortage of agricultural labor necessitates the development of predictive models to optimize farm operations. This study investigates the effectiveness of artificial-intelligence-driven models to accurately forecast the timing and yield of persimmon harvests, using meteorological data alongside historical harvest records. An artificial neural network was designed to estimate peak harvest dates by analyzing key meteorological variables. The model was trained and validated using data from the JA Nara Prefecture Nishiyoshino Sorting Facility and Nara Prefecture Agriculture Research and Development Center. Its reliability was confirmed based on mean absolute error, demonstrating the ability to make predictions with an accuracy of approximately three days. Additionally, extreme gradient boosting models were developed to predict yields, incorporating elevation data to refine predictions at the field scale. The model was trained and validated using data from fields cultivated in the Gojo-Yoshino region. The effectiveness of these models was evaluated using root mean square error, demonstrating an improvement in prediction accuracy of up to 20% with the inclusion of elevation data, illustrating their capability to effectively capture yield variations across different orchards. These models can significantly improve labor management, harvest scheduling, and overall productivity within the realm of smart agriculture. Full article

Agricultural land classification plays a pivotal role in food security and ecological sustainability, yet achieving accurate large-scale mapping remains challenging. This study presents methodological innovations through a multi-level feature enhancement framework that transcends traditional time series analysis. Using Shandong Province, northern China’s agricultural heartland, as a case study, we first established a foundation with time series red-edge vegetation indices (REVI) from Sentinel-2 imagery, uniquely combining the normalized difference red edge index (NDRE₇₀₅) and plant senescence reflectance index (PSRI). Moving beyond conventional time series analysis, we innovatively amplified key temporal characteristics through newly designed spatial feature parameters (SFPs) and phenological feature parameters (PFPs). This strategic enhancement of critical temporal points significantly improved classification performance by capturing subtle spatial patterns and phenological transitions that are often overlooked in traditional approaches. The study yielded three significant findings: (1) The synergistic application of NDRE₇₀₅ and PSRI significantly outperformed single-index approaches, demonstrating the effectiveness of our dual-index strategy; (2) The integration of SFPs and PFPs with time series REVI markedly enhanced feature discrimination at crucial growth stages, with PFPs showing superior capability in distinguishing agricultural land types through amplified phenological signatures; (3) Our optimal classification scheme (FC6), leveraging both enhanced spatial and phenological features, achieved remarkable accuracy (93.21%) with a Kappa coefficient of 0.9159, representing improvements of 4.83% and 0.0538, respectively, over the baseline approach. This comprehensive framework successfully mapped 120,996 km² of agricultural land, differentiating winter wheat–summer maize rotation areas (39.44%), single-season crop fields (36.16%), orchards (14.49%), and facility vegetable fields (9.91%). Our approach advances the field by introducing a robust, scalable methodology that not only utilizes the full potential of time series data but also strategically enhances critical temporal features for improved classification accuracy, particularly valuable for regions with complex farming systems and diverse crop patterns. Full article

Agroforestry production systems have shown growing adoption in Bangladesh, offering ecological and economic benefits in the face of climate change. This study investigates the scale of agroforestry adoption, investment returns, factors influencing uptake, and challenges faced by farmers. Using a multistage random sample of 340 respondents, we find that while 75% of farmers are aware of agroforestry, adoption remains limited. Our analysis focuses on specific tree–crop combinations favored by farmers as agroforestry practices. The results demonstrate that, in cropland agroforestry, Eucalyptus tree with rice (69.05% adoption rate) is predominant, while homestead/orchard system agroforestry favors mango tree intercropped with potato (73.33%). Financial and investment analyses using Benefit–Cost Ratio (BCR), Net Present Value (NPV), and Internal Rate of Return (IRR) prove that agroforestry is a more favorable alternative for farmers considering adoption, as it provides superior BCR, NPV, and IRR. For example, litchi-based agroforestry systems with vegetables like brinjal (eggplant), potato, and chilies offer higher NPVs (19.00, 19.73, and 18.46, respectively) and IRRs (54.45, 68.00, and 47.19, respectively) compared to monocropping where NPV was 14.38. A binary logistic model reveals that larger farm sizes, younger respondents, higher education levels, training experiences, more frequent extension visits, and improved market access positively influence agroforestry adoption. The study also identifies key challenges for farmers using the Problem Facing Index (PFI). The most significant obstacles include lack of training facilities (PFI-894), shortage of skilled labor (PFI-687), and insufficient technical expertise (PFI-647). Therefore, to promote wider adoption, targeted training programs that address the identified challenges are crucial. It will empower farmers to reap the tangible benefits of agroforestry as a sustainable and climate-smart agricultural practice. Full article

Site selection and allocation of manufacturing and processing facilities are essential to sustainable economic productivity of a given product while preserving soil, the environment, and biodiversity. An essential criterion when evaluating various approaches to model land suitability for pistachio processing facilities is their adaptability to accommodate diverse perspectives and circumstances of managers and decision makers. Incorporating the concept of risk into the decision-making process stands as a significant research gap in modeling land suitability for pistachio processing facilities. This study presents a scenario-based multi-criteria decision-making system for modeling the land suitability of pistachio processing facilities. The model was implemented based on a stakeholder analysis as well as inclusion of a set of influential criteria and restrictions for an Iranian case study, which is among the top three producers. The weight of each criterion was determined based on the best-worst method (BWM) after the stakeholder analysis. Then, the ordered weighted averaging (OWA) model was used to prepare maps of spatial potential for building a pistachio processing factory in different decision-making scenarios, including very pessimistic, pessimistic, intermediate, optimistic, and very optimistic attitudes. Finally, the sensitivity analysis of very-high- and high-potential regions to changes in the weight of the effective criteria was evaluated and proved that the most important criteria were proximity to pistachio orchards, proximity to residential areas, proximity to the road network, and proximity to industrial areas. Overall, 327 km² of the study area was classified as restricted, meaning that they are not suitable locations for pistachio processing. The average estimated potential values based on the proposed model for very pessimistic, pessimistic, intermediate, optimistic, and very optimistic scenarios were 0.19, 0.47, 0.63, 0.78, and 0.97, respectively. The very-high-potential class covered 0, 0.41, 8.25, 39.64, and 99.78 percent of the study area based on these scenarios, respectively. The area of suitable regions for investment decreased by increasing risk aversion in decision making. The model was more sensitive to changes in the weights of proximity to residential areas, proximity to pistachio orchards, and proximity to transportation hubs. The proposed approach and the achieved findings could be of broader use to respective stakeholders and investors. Given the suitability of arid regions for planting pistachio and its relatively high profitability, the local authorities and decision makers can promote further expansion of the orchards, which can lead to better welfare of farmers and reducing rural-urban migration in the region. Full article

Monilinia laxa, a notorious fungal pathogen responsible for the devastating brown rot disease afflicting apples, wreaks havoc in both orchards and storage facilities, precipitating substantial economic losses. Currently, chemical methods represent the primary means of controlling this pathogen in warehouses. However, this study sought to explore an alternative approach by harnessing the biocontrol potential of bacterial isolates against brown rot in apple trees. A total of 72 bacterial isolates were successfully obtained from the apple tree rhizosphere and subjected to initial screening via co-cultivation with the pathogen. Notably, eight bacterial isolates demonstrated remarkable efficacy, reducing the mycelial growth of the pathogen from 68.75 to 9.25%. These isolates were subsequently characterized based on phenotypic traits, biochemical properties, and 16S rRNA gene amplification. Furthermore, we investigated these isolates’ production capacity with respect to two enzymes, namely, protease and chitinase, and evaluated their efficacy in disease control. Through phenotypic, biochemical, and 16S rRNA gene-sequencing analyses, the bacterial isolates were identified as Serratia marcescens, Bacillus cereus, Bacillus sp., Staphylococcus succinus, and Pseudomonas baetica. In dual culture assays incorporating M. laxa, S. marcescens and S. succinus exhibited the most potent degree of mycelial growth inhibition, achieving 68.75 and 9.25% reductions, respectively. All the bacterial isolates displayed significant chitinase and protease activities. Quantitative assessment of chitinase activity revealed the highest levels in strains AP5 and AP13, with values of 1.47 and 1.36 U/mL, respectively. Similarly, AP13 and AP6 exhibited the highest protease activity, with maximal enzyme production levels reaching 1.3 and 1.2 U/mL, respectively. In apple disease control assays, S. marcescens and S. succinus strains exhibited disease severity values of 12.34% and 61.66% (DS), respectively, highlighting their contrasting efficacy in mitigating disease infecting apple fruits. These findings underscore the immense potential of the selected bacterial strains with regard to serving as biocontrol agents for combatting brown rot disease in apple trees, thus paving the way for sustainable and eco-friendly alternatives to chemical interventions. Full article

The effective quantification of deposition rate is of vital importance in optimizing the application performance and the utilization of pesticides; meanwhile, the canopies of fruit tree orchards are large, with dense branches and leaves shading each other, making it difficult to quantify spraying efficiency. Therefore, it is imperative to develop a facile methodology for assessing the performance of different spraying techniques in terms of distribution and utilization rate in orchards. To evaluate spraying efficacy in orchards, a canopy segmentation method was developed in to be able to determine the spray deposition rate. The distribution and deposition rate of spray liquid applied using three kinds of orchard sprayer were measured in a pear orchard and a peach orchard. The test results showed that the trailer sprayer had the highest deposition rates, with values of 31.54% and 56.92% on peach and pear trees, respectively. The deposition rates of the mounted sprayer in the peach and pear canopies were 21.75% and 40.61%, and the rates of the hand-held sprayer were 25.19% and 29.97%, respectively. The spray gun had the best droplet distribution uniformity, with CVs of the spray in the peach and pear canopies of 20.54% and 25.06%, respectively. The CVs in the peach and pear canopies were 35.98% and 26.54% for the trailer sprayer, and the CVs of the mounted sprayer were 92.52% and 94.90%, respectively. The canopy segmentation method could effectively be used to calculate the deposition rate and drioplet distribution in orchard application, while a great deal of time was consumed by counting the number of leaves in the different areas of the fruit tree canopies. Therefore, research on the density of branches and leaves in fruit tree canopies should be carried out in order to improve the efficiency of fruit tree canopy information extraction. Full article

Due to the unique geographical location and rapid development in the agricultural industry, heavy metals’ risk of soil contamination in the Qaidam Basin is gradually increasing. The following study was conducted to determine the soil heavy metal contents under different types of land use, contamination levels, and the physicochemical properties of soil. Soil samples were collected from facility lands, orchards, farmlands, and grasslands at 0–10 and 10–20 cm soil layers. Heavy metals including copper (Cu), chromium (Cr), nickel (Ni), zinc (Zn), lead (Pb), cadmium (Cd), arsenic (As), and mercury (Hg) were analyzed using inductively coupled plasma mass spectrometry and the soil was evaluated with different methods. Overall, the average Cu (25.07 mg/kg), Cr (45.67 mg/kg), Ni (25.56 mg/kg), Zn (71.24 mg/kg), Pb (14.19 mg/kg), Cd (0.17 mg/kg), As (12.54 mg/kg), and Hg (0.05 mg/kg) were lower than the environmental quality standard. However, the Cu, Cr, Ni, and As were highest in farmland, and Zn and Hg were highest in the facility land. The Pb content was highest in orchards, and the Cd content was the same in facility land, orchards, and farmland. Among the different land-use types, the soil heavy metal concentrations decreased in the order of facility land > farmland > grassland > orchards. The pH was alkaline, the content of SOC (soil organic carbon) 15.76 g/kg in grassland, TN (total nitrogen) 1.43 g/kg, and TP (total phosphorus) 0.97 g/kg in facility land showed the highest result. The soil BD (bulk density) had a significant positive correlation with Cu, Cr, Ni, Zn, Pb, Cd, and the TP positively correlated with Cu, Zn, Cd, and Hg. The soil evaluation results of the comprehensive pollution index indicated that the soil was in a clean condition. The index of potential environmental risk indicates that heavy metals are slightly harmful to the soil. Full article

The accurate detection of canopy characteristics is the basis of precise variable spraying. Canopy characteristics such as canopy density, thickness and volume are needed to vary the pesticide application rate and adjust the spray flow rate and air supply volume. Canopy thickness is an important canopy dimension for the calculation of tree canopy volume in pesticide variable spraying. With regard to the phenomenon of ultrasonic waves with multiple reflections and the further analysis of echo signals, we found that there is a proportional relationship between the canopy thickness and echo interval time. In this paper, we propose a method to calculate canopy thickness using echo signals that come from ultrasonic sensors. To investigate the application of this method, we conducted a set of lab-based experiments with a simulated canopy. The results show that we can accurately estimate canopy thickness when the detection distance, canopy density, and canopy thickness range between 0.5and 1.5 m, 1.2 and 1.4, and 0.3and 0.6 m, respectively. The relative error between the estimated value and actual value of the simulated canopy thickness is no higher than 8.8%. To compare our lab results with trees in the field, we measured canopy thickness from three naturally occurring Osmanthus trees (Osmanthus fragrans Lour). The results showed that the mean relative errors of three Osmanthus trees are 19.2%, 19.4% and 18.8%, respectively. These results can be used to improve measurements for agricultural production that includes both orchards and facilities by providing a reference point for the precise application of variable spraying. Full article

The decline of relative chlorophyll contents during fruit ripening is considered to be an important indicator of fruit physiological condition. The recent availability of low-cost portable visible spectrum (VIS) spectrometers has spurred research interest towards optical sensing of chlorophyll changes in intact fruit, with many scientists attempting to link the shifts in optical signals, attributed to chlorophyll changes, to different maturity and quality parameters. One of the widely available portable devices for non-destructive estimation of relative chlorophyll contents is the DA meter, which provides a maturity index that is calculated as a difference between absorption at 670 nm (near the chlorophyll-a absorption peak) and 720 nm (background of the spectrum), abbreviated as IAD. In the present study, the evolution of IAD and its relation to starch pattern index (SPI) and fruit flesh firmness (FFF) was monitored in fruit of two cv. ‘Gala’ clones during maturation and storage, aiming to identify a potential existence of a usable IAD range for the assessment and prediction of the optimal harvest window and storage potential. In both clones, canopy positions, fruit sides, and seasons IAD, SPI, and FFF generally changed in a linear fashion over time, but with partially very different slopes, i.e., they were changing at different rates. What all of these parameters had in common was the presence of a very high biological variability, which is typical of apple fruit. Significantly powerful estimations of SPI (r² > 0.7, p < 0.005) and pre- and post-storage FFF (r² > 0.6, p < 0.005) were achieved. However, the very large biological variability could not be neutralized, which means that the predictions always included large confidence intervals of up to 0.46–0.59 units for SPI and 0.82–1.1 kgF FFF, which ultimately makes them unusable for practical applications. Experiments done under real-life conditions in a commercial fruit storage facility on several different fruit batches confirmed that IAD measured at harvest cannot be used indiscriminately for predicting post-storage FFF of cv. ‘Gala’ originating from different orchards. Nevertheless, mean IAD values that were obtained at optimal maturity from samples of the same orchards remained stable over seasons (0.8–1.2), which strongly suggests that, provided that the calibrations and validations are not only cultivar, but also orchard-specific, IAD has a potential for estimating maturity and storability of apple fruit. In this case, IAD could replace standard maturity indices, otherwise it would be suited for use as a supplementary index for determining fruits physiological maturity status. Full article